Changeable Manufacturing Processes using Service-Based Decision-Making and I4.0 Service-Oriented Architecture

Traditional manufacturing systems are suitable for mass production with low diversity. Since they have hard coded control logic, reconfiguration for new production tasks becomes difficult after deployment. In this paper, we present a novel architecture of a decision-making engine that derives an optimal or near optimal execution strategy leveraging an I4.0 service-oriented architecture. The execution strategy for manufacturing processes consists of a routing policy and a scheduling strategy. The engine analyses the current overall condition of the plant with regard to production progress and pending tasks and evaluates the potential solutions using discrete-event simulation. By applying a two-level search method, our approach is able to identify an optimized production strategy within a reasonable time. This enables the manufacturing system to react flexibly to new production orders and to integrate them into running production processes, which in particular also enables profitable realization of small lot sizes. To show the feasibility of our approach, we also show our validation activities.